no code implementations • WASSA (ACL) 2022 • Diogo Silva, David Semedo, João Magalhães
In this paper, we conduct a novel assessment of politeness strategies for task-oriented dialog agents under a transfer learning scenario.
no code implementations • 5 Apr 2024 • João Coelho, Bruno Martins, João Magalhães, Jamie Callan, Chenyan Xiong
This study investigates the existence of positional biases in Transformer-based models for text representation learning, particularly in the context of web document retrieval.
no code implementations • 20 Feb 2024 • Ricardo Lopes, João Magalhães, David Semedo
We introduce Gl\'orIA, a robust European Portuguese decoder LLM.
no code implementations • 9 Feb 2024 • João Daniel Silva, João Magalhães, Devis Tuia, Bruno Martins
In this work, we propose RS-CapRet, a Vision and Language method for remote sensing tasks, in particular image captioning and text-image retrieval.
no code implementations • 1 Feb 2024 • Diogo Glória-Silva, Rafael Ferreira, Diogo Tavares, David Semedo, João Magalhães
In this paper, we tackle a dual goal mixed-initiative conversational setting where the LLM not only grounds the conversation on an arbitrary plan but also seeks to satisfy both a procedural plan and user instructions.
no code implementations • 3 Oct 2023 • Rafael Ferreira, Diogo Tavares, Diogo Silva, Rodrigo Valério, João Bordalo, Inês Simões, Vasco Ramos, David Semedo, João Magalhães
In this report, we describe the vision, challenges, and scientific contributions of the Task Wizard team, TWIZ, in the Alexa Prize TaskBot Challenge 2022.
1 code implementation • 20 Sep 2023 • Rafael Ferreira, David Semedo, João Magalhães
Hence, when conversational assistants walk users through the steps of complex tasks, there is a need to structure the task into manageable pieces of information of the right length and complexity.
1 code implementation • 20 Sep 2023 • Rafael Ferreira, David Semedo, João Magalhães
Predicting the success of Conversational Task Assistants (CTA) can be critical to understand user behavior and act accordingly.
no code implementations • 20 Sep 2023 • Frederico Vicente, Rafael Ferreira, David Semedo, João Magalhães
Introducing curiosities in a conversation is a way to teach something new to the person in a pleasant and enjoyable way.
no code implementations • 11 Aug 2023 • Diogo Tavares, Pedro Azevedo, David Semedo, Ricardo Sousa, João Magalhães
Dialogue systems need to deal with the unpredictability of user intents to track dialogue state and the heterogeneity of slots to understand user preferences.
no code implementations • 14 Apr 2021 • Mariana Leite, Rafael Ferreira, David Semedo, João Magalhães
In this work, we propose a knowledge-driven answer generation approach for open-domain conversational search, where a conversation-wide entities' knowledge graph is used to bias search-answer generation.
no code implementations • 30 Sep 2019 • David Semedo, João Magalhães
Cross-modal embeddings, between textual and visual modalities, aim to organise multimodal instances by their semantic correlations.